Shut down the app when the listener fails (closes #200) (#218)

internal/server/server.go

@@ -50,6 +50,13 @@ const (
 	minSentryFlush = 250 * time.Millisecond
 )
 
+// ListenFailureExitCode is the status the process exits with when the
+// HTTP listener cannot be established, or dies for a reason other
+// than a requested shutdown. It must stay non-zero: systemd
+// `Restart=on-failure` and Docker's restart policies key off it, and a
+// zero exit would read as a deliberate stop.
+const ListenFailureExitCode = 1
+
 // SentryFlushBudget reports how long the Sentry flush may run when
 // remaining is the time left on the fx stop context after the HTTP
 // drain. sentry.Flush takes a bare duration and honours no context,
@@ -75,13 +82,13 @@ type ServerParams struct {
 	Config     *config.Config
 	Middleware *middleware.Middleware
 	Handlers   *handlers.Handlers
+	Shutdowner fx.Shutdowner
 }
 
 // Server is the main HTTP server that wires up routes and manages
 // graceful shutdown.
 type Server struct {
 	startupTime   time.Time
-	exitCode      int
 	sentryEnabled bool
 	log           *slog.Logger
 	cancelFunc    context.CancelFunc
@@ -159,7 +166,12 @@ func (s *Server) enableSentry() {
 	s.sentryEnabled = true
 }
 
-func (s *Server) serve() int {
+// serve installs the signal watcher, starts the listener and blocks
+// until the server's context is cancelled. The process exit status is
+// fx's to decide — from a signal, or from the code
+// shutdownOnListenFailure hands the Shutdowner — so this reports
+// nothing back to its caller.
+func (s *Server) serve() {
 	ctx, cancelFunc := context.WithCancel(context.Background())
 	s.cancelFunc = cancelFunc
 
@@ -185,7 +197,30 @@ func (s *Server) serve() int {
 	<-ctx.Done()
 	// Shutdown is handled by the fx OnStop hook (cleanShutdown).
 	// Do not call cleanShutdown() here to avoid double invocation.
-	return s.exitCode
+}
+
+// shutdownOnListenFailure ends the application after the HTTP
+// listener failed. The fx OnStart hook returns as soon as the serving
+// goroutine is spawned, so nothing downstream of it ever learns that
+// the listen failed: fx reports RUNNING and the process sits alive
+// with nothing bound, which is invisible to systemd and Docker
+// restart policies. Asking the Shutdowner to stop the app with a
+// non-zero code is what turns that into a visible failure.
+//
+// The context cancel that follows only unwinds serve()'s own wait.
+// The shutdown itself runs through fx's normal stop sequence, so the
+// clean-shutdown drain in cleanShutdown is reached unchanged.
+func (s *Server) shutdownOnListenFailure() {
+	err := s.params.Shutdowner.Shutdown(
+		fx.ExitCode(ListenFailureExitCode),
+	)
+	if err != nil {
+		s.log.Error("shutdown request failed", "error", err)
+	}
+
+	if s.cancelFunc != nil {
+		s.cancelFunc()
+	}
 }
 
 func (s *Server) cleanupForExit() {
@@ -193,9 +228,6 @@ func (s *Server) cleanupForExit() {
 }
 
 func (s *Server) cleanShutdown(ctx context.Context) {
-	// initiate clean shutdown
-	s.exitCode = 0
-
 	ctxShutdown, shutdownCancel := context.WithTimeout(
 		ctx, ShutdownTimeout,
 	)